KR101072033B1 - Search method and system based uses - Google Patents

Abstract

Disclosed are a search method based on a use and a system for performing the method. A search system based on a usage includes an indicator module for generating at least one indicator by indexing an attribute and an association of a keyword; An indicator selection module that selects at least one of the indicators as a weighting indicator in correspondence to a use of the keyword; A weight correction module for changing an index value by applying a weight to the weight indicator; A simulation module for evaluating the keyword based on the weight indicator of the keyword and the indicator, and a search module for providing a keyword suitable for the purpose based on the evaluation of the keyword.

Weights, directionality, indicators, keywords, ranking scores.

Description

Search method and system based on usage {SEARCH METHOD AND SYSTEM BASED USES}

The present invention relates to a search method based on a use and a system for performing the method.

The conventional keyword search method uses a method of searching for and providing a keyword that matches or resembles the keyword in response to the keyword.

However, there is a limit in that it is difficult to accurately search for a keyword suitable for the specific purpose of searching for a keyword necessary for a specific purpose rather than an associated keyword.

In addition, the conventional keyword search method has a problem that only specific keywords are repeatedly searched and new keywords are difficult to search because the search criteria are similar.

Therefore, it is possible to search for a suitable keyword for each purpose in response to the purpose for which the keyword can be used, and to search for a keyword with a low number other than the relevance, a method or system for searching more new keywords is needed. It is true.

The present invention weights at least one indicator suitable for a usage purpose of a keyword, and selects and provides a keyword based on an indicator including a weighted indicator. Provide a search system based on the above.

The present invention provides a retrieval system based on a use purpose of identifying important keywords that are not selected because some of the indicator values are low by changing the priority according to each indicator value.

According to an embodiment of the present invention, a search system based on a usage purpose includes: an indicator module configured to generate at least one indicator by indicating an attribute and an association of a keyword; An indicator selection module that selects at least one of the indicators as a weighting indicator in correspondence to a use of the keyword; A weight correction module for changing an index value by applying a weight to the weight indicator; And a simulation module for evaluating the keyword based on the weight indicator of the keyword and the indicator, and a search module for providing a keyword suitable for the purpose based on the evaluation of the keyword.

According to an aspect of the present invention, the indicator selection module identifies a significant point corresponding to a use of the keyword, sets the directionality of a condition necessary for the use of the keyword based on the important point, At least one indicator may be selected based on the indicators.

According to one aspect of the invention, the simulation module may evaluate the effect of the keyword provided by the search module using a specific indicator.

According to an aspect of the present invention, the simulation module generates a ranking logic evaluation indicator based on the weight indicator and the indicator, classifies the indicator included in the ranking logic evaluation indicator, and corresponds to the values of the classified indicator. The priority and ratio of keywords can be corrected.

According to an aspect of the present invention, if the values of the entry indicator and the competition indicator are low and the values of the service indicator, the conversion indicator, and the related indicator are high, the priority is determined as a keyword necessary to increase the scatter map. Can be corrected with

According to an aspect of the present invention, the simulation module may select a representative keyword from among the keywords having a high value of the service indicator, the conversion indicator, and the related indicator.

According to an aspect of the present invention, the keyword may be included in a keyword pool that further includes keywords extracted from other sources in the set of sales top keywords classified by business type.

According to an aspect of the present invention, the keywords included in the keyword pool may be keywords classified according to the keyword industry and the advertiser industry.

A search method based on a usage purpose according to an embodiment of the present invention may include generating at least one index by indexing an attribute and an association of a keyword; Selecting at least one indicator from among the indicators as a weighting indicator corresponding to a purpose of using the keyword; Changing an indicator value by applying a weight to the weight indicator; Evaluating the keyword based on the weight indicator and the indicator of the keyword and providing a keyword suitable for the purpose based on the evaluation of the keyword.

According to the present invention, a keyword suitable for the intended use can be searched by weighting at least one index suitable for the intended use of the keyword, and selecting and providing a keyword based on the indicator including the weighted indicator.

According to the present invention, by changing the priority according to each indicator value, it is possible to discover important keywords that are not selected because some of the indicator values are low.

Hereinafter, various embodiments of the present disclosure will be described in detail with reference to the accompanying drawings.

1 is a block diagram of a search system based on a usage purpose according to an embodiment of the present invention.

Referring to FIG. 1, when the search system 100 based on a usage purpose generates the at least one index by indexing the attribute and association of the keyword, the index selection module 102 uses the keyword to be used. If at least one of the indicators is selected as the weighting indicator in response to the weighting, and the weight correction module 103 changes the value of the indicator by applying a weight to the weighting indicator, the simulation module 104 is the weight of the keyword The use of the keyword is evaluated based on the indicator and the indicator, and the search module 105 provides a keyword suitable for the use based on the evaluation of the keyword.

The index module 101 may index the keywords included in the keyword pool formed by enlarging the set of keywords whose sales amount is higher.

In this case, the keyword may be a keyword included in the set of 10,000 keywords of the top sales of the business category, the keyword pool may be formed by further including a keyword extracted from another source in the set of the top sales keywords.

In this case, the other source may include at least one of a keyword that generates a predetermined number of views for each keyword, news, blogs, intellectuals, shopping, site crawling, shopping mall query information, and issue keyword.

In addition, keywords included in the keyword pool may be suitable for indexing by being classified according to the keyword industry and the advertiser industry.

The indicator selection module 102 identifies a significant point corresponding to the purpose for which the keyword is to be used, sets the directionality of a condition necessary for the purpose in which the keyword is to be used based on the significant point, and based on the directionality, at least one of the indexes. You can select one indicator.

The simulation module 104 may generate a ranking logic evaluation index for evaluating the use of the keyword before the keyword is provided and a quality evaluation index for evaluating the effect of the keyword to be used after the keyword is provided based on the weight index and the index.

The simulation module 104 may classify the indexes included in the ranking logic evaluation indexes, and correct the priority and ratio of the keywords corresponding to the values of the classified indexes. In this case, the ranking logic evaluation indicators are competition indicators indicating the competition of the advertisement, service indicators indicating the visit amount of the user, conversion indicators indicating the click-through rate versus impressions, association indicators indicating the degree of association, and entry indicators indicating the difficulty of the entry barrier It may include at least one of the.

The competition index may determine that the lower the value obtained by dividing the number of registered advertisements by the number of registered advertisers, the lower the PPC value may be determined. In addition, the service index may be determined that the higher the value divided by the number of clicks QC, the higher the CTR value, the conversion indicator may be determined, the higher the associated index may be determined that the higher the associated score. have.

In addition, the simulation module 104 uses keywords provided using a quality evaluation index including a coverage table indicating whether actual advertisement registration is made using the recommendation tool and a sales index indicating whether the sales of the keywords provided in step S206 have increased. Can be evaluated. In this case, the coverage table may be a value obtained by dividing the number of registered advertisements by the number of registered advertisers.

In addition, the simulation module 104 determines that the priority of the highest priority is determined as a keyword necessary to increase the scatter when the values of the service indicator, the conversion indicator, and the related indicator are high while the values of the entry indicator and the competition indicator are low. If the values of the entry indicator and the competition indicator are high and the values of the service indicator, the conversion indicator, and the related indicator are low, the priority indicator may be corrected by determining a keyword necessary for promotion. .

In addition, the simulation module 104 may select a representative keyword from among the keywords having a high value of the service indicator, the conversion indicator, and the related indicator.

2 is a flowchart illustrating a search method based on a use purpose in an embodiment of the present invention.

In step S201, the indicator module 101 generates, as an indicator, an association between an attribute of a keyword and another keyword.

In this case, the index module 101 may generate an independent index by indexing its own attribute of the keyword, and generate an index of index by indexing the correlation between keywords of different keywords.

In step S202, the indicator selection module 102 sets the direction of which indicator is suitable for the use purpose based on the important point for each use purpose of the keyword.

In this case, the indicator selection module 102 may identify a significant point corresponding to the purpose for which the keyword is to be used, and set the direction of a condition necessary for the purpose for which the keyword is to be used based on the significant point.

The process of setting the directionality will be described in more detail with reference to FIG. 3.

In operation S203, the indicator selection module 102 selects at least one indicator generated in operation S201 based on the direction set in operation S202 in response to the usage of the keyword.

The process of selecting the indicator will be described in more detail with reference to FIG. 4.

In step S204, the weight correction module 103 corrects by applying a weight to the value of the indicator selected in step S203.

At this time, the weight may be set differently for each indicator according to the importance of the indicator in the use of the keyword.

In step S205, the simulation module 104 evaluates the use of the keyword based on the weight indicators corrected in step S204 and the indicators generated in step S201 and not corrected by applying weights.

In this case, the simulation module 104 may classify the indexes included in the ranking logic evaluation indexes, and correct the priority and ratio of the keywords corresponding to the values of the classified indexes. In this case, the ranking logic evaluation indicators are competition indicators indicating the competition of the advertisement, service indicators indicating the visit amount of the user, conversion indicators indicating the click-through rate versus impressions, association indicators indicating the degree of association, and entry indicators indicating the difficulty of the entry barrier It may include at least one of the.

In this case, the competition index may determine that the lower the value obtained by dividing the number of registered advertisements by the number of registered advertisers, and the entry indicator may determine that the lower the PPC value is, the better. In addition, the service index may be determined that the higher the value divided by the number of clicks QC, the higher the CTR value, the conversion indicator may be determined, the higher the associated index may be determined that the higher the associated score. have.

The simulation module 104 may select a representative keyword from among the keywords having a high value of the service index, the conversion index, and the related index.

In this case, the simulation module 104 determines that the keyword is necessary to increase the degree of dispersion when the values of the service indicator, the conversion indicator, and the related indicator are high while the values of the entry indicator and the competition indicator are low, and the priority is determined as the highest priority. If the values of the entry indicator and the competition indicator are high and the values of the service indicator, the conversion indicator, and the related indicator are low, the priority indicator may be corrected by determining the keyword necessary for promotion.

In this case, a process of evaluating the use of the keyword will be described in more detail with reference to FIG. 5.

In step S206, the search module 105 provides a keyword suitable for the purpose based on the evaluation of the keyword evaluated in step S205.

In step S207, the simulation module 104 evaluates the keyword provided in step S205.

In this case, the simulation module 104 may evaluate using a quality evaluation index including a coverage table indicating whether actual advertisement registration is made using the recommendation tool and a sales index indicating whether the sales of the keywords provided in step S206 have increased. have. In this case, the coverage table may be a value obtained by dividing the number of registered advertisements by the number of registered advertisers.

As such, a search method based on the identified use purpose will be described in more detail with reference to FIGS. 3, 4, and 5.

3 is an example of a process of setting the direction of a keyword according to an embodiment of the present invention.

Referring to FIG. 3, a process of setting the direction of a keyword 311 for use as a keyword station, a keyword 321 for use as a recommendation service application, and a keyword 331 for use as a SPM can be confirmed.

The important point 312 of the keyword 311 whose usage is for the keyword station is that the kurtosis should be lowered and the scattering degree increased in the competitiveness of the recommended keyword or the distribution of the PPC as shown in FIG. This may include increasing the likelihood of this happening.

In this case, the indicator selection module 102 includes conditions such as 'is there a possibility of sales', 'a barrier to entry or registration is low', and 'a reflection of the manager's adjustment' based on the critical point 312. The directionality 313 can be set in the keyword 311 whose usage is for the keyword station.

The important point 322 of the keyword 321 for the use of the recommendation service may be to minimize an advertiser protest due to the occurrence of Abbush as shown in FIG. 4 and to reflect the usage pattern of the service user as much as possible. have.

At this time, the indicator selection module 102 based on the critical point 322, directionality 323 including the conditions 'Availing data is excluded,' 'QQ correlation is well reflected', and 'Well filtered?' ) Can be set in the keyword 321 whose use is for the recommendation service application.

Key points 332 of the keyword 331 for the purpose of using SPM may include maximizing the relevance and scalability as shown in FIG. 4, and reflecting the keyword with the expanded exposure and the revenue generated in the annual score. have.

At this time, the indicator selection module 102 is based on the critical point 332, the conditions of 'Is there a lot of clicks are likely to click on exposure,' 'QQ relevance was well reflected', and 'Is the exposure to maximize sales' The included directionality 333 can be set in the keyword 331 whose usage is for SPM.

4 is an example of a process of selecting an indicator for each purpose of use according to an embodiment of the present invention.

As shown in FIG. 4, the indicator selecting module 102 uses the directionality for the usage purposes 421, 422, and 423 set in step S202 to increase the weight in the indicators 410 generated in step S201. , 432, 433).

In the case where the usage purpose is the keyword station 421, the direction set in step S202 is whether there is a possibility of sales on the basis of whether the entry barrier of registration or execution is low and whether the manager's adjustment is well reflected. Accordingly, the indicator selection module 102 selects a competitive index in response to the low entry barrier of registration or execution, selects a purchase related index and a sales index in response to whether there is a possibility of revenue, and reflects the adjustment of the manager. You can choose the material context-related indicators in response to your well being.

In the case where the usage purpose is the recommendation service application 422, the direction set in step S202 is whether the abusing data is excluded, QQ relevance is well reflected, and filtering is performed on the basis. Accordingly, the indicator selection module 102 selects the Proportion Ratio Indicator in response to whether the abusing data is excluded and the filtering is good, and selects the Query Association Index and the Hit Index in response to whether the QQ relevance is well reflected. Can be.

In the case where the use purpose is the SPM 423, the directions set in step S202 include a high probability of a click on an exposure, a good reflection of the QQ association, and an exposure that can maximize sales. Accordingly, the indicator selection module 102 may select an impression association indicator in response to whether the impression is likely to be clickable and an impression that can maximize sales, and select a query association indicator in response to whether the QQ relevance is well reflected. have.

5 is an example of a process of evaluating the use of a keyword according to an embodiment of the present invention.

The simulation module 104 groups the entry indicators and the competition indicators into indicator group 1, groups the service indicators, the conversion indicators, and the related indicators into indicator group 2. Based on the value and the value of the indicator included in the indicator group 2, the keywords are assigned to the A1 group 501, the A2 group, the A3 group 502, the B1 group, the B2 group, the B3 group, and the C1 as shown in FIG. Group 503, group C2, group 504.

The competition index may determine that the lower the value obtained by dividing the number of registered advertisements by the number of registered advertisers, the lower the PPC value may be determined. In addition, the conversion indicator may determine that the higher the CTR value, the higher the association score may determine that the better, and the service indicator may determine that the higher the value divided by QC by the number of clicks. Can be.

In this case, the simulation module 104 uses the keyword included in the A3 group 502 having a low value of the indicator included in the indicator group 1 and having a high value of the indicator included in the indicator group 2 as a keyword necessary to increase the scatter. By judging, the priority is corrected to the first priority, and the keywords included in the A1 group 501 having high values of the indicators included in the indicator group 1 and the indicator group 2 are high in importance, but are judged as keywords that are already registered. Can be corrected to second order.

In addition, the simulation module 104 determines the keyword included in the C1 group 503 having a high value of the indicator included in the indicator group 1 and having a low value of the indicator included in the indicator group 2 as a keyword necessary for promotion. The ranking is corrected to three ranks, and the keywords included in the C3 group 504 having low values of the indicators included in the indicator group 1 and the indicator group 2 are determined to be low priority keywords, and thus the priority is corrected to the fourth rank. Can be.

In this case, the simulation module 104 may adjust a ratio of providing a keyword in response to the priority.

6 is a flowchart illustrating a method of classifying a business type of a keyword to be indexed by the indicator module 101 according to an exemplary embodiment of the present invention.

In step S601, the indicator module 101 extracts 10,000 keywords of the top sales.

In step S602, the indicator module 101 classifies the keywords extracted in step S601.

In this case, the indicator module 101 may manually classify the keyword extracted in step S601 by item or industry type.

In step S603, the indicator module 101 enlarges the set of keywords classified in step S601 to generate a keyword pool.

In this case, the indicator module 101 may further include a keyword extracted from another source in the set of the top sales keywords to form a keyword pool. In this case, the other source may include at least one of a keyword that generates a predetermined number of views for each keyword, news, blogs, intellectuals, shopping, site crawling, shopping mall query information, and issue keyword.

In step S604, the indicator module 101 adjusts the keyword pool generated in step S603.

In this case, the indicator module 101 may add a keyword corresponding to a specific condition to the keyword pool or remove a keyword that does not satisfy a specific condition among the keywords included in the keyword pool.

In step S604, the indicator module 101 classifies keywords included in the keyword pool adjusted in step S604 by type of industry.

In this case, the indicator module 101 may generate an industry type indicator for each keyword and group keywords of similar industries.

In step S605, the indicator module 101 classifies keywords included in the keyword pool adjusted in step S604 by advertiser industry.

In this case, the indicator module 101 may generate an advertiser type indicator for each keyword and group similar keywords for the similar advertiser type or the same advertiser.

A search system based on a usage purpose may provide a keyword suitable for the intended use by weighting at least one indicator suitable for the intended use of the keyword, and selecting and providing the keyword based on the indicator including the weighted indicator. In addition, by changing the priority according to each indicator value, it is possible to discover and provide important keywords that were not selected because some indicator values are low.

Embodiments according to the present invention can be implemented in the form of program instructions that can be executed by various computer means can be recorded on a computer readable medium. The computer readable medium may include program instructions, file data, data structures, etc. alone or in combination. Program instructions recorded on the media may be those specially designed and constructed for the purposes of the present invention, or they may be of the kind well-known and available to those having skill in the computer software arts. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tape, optical media such as CD-ROMs, DVDs, and magnetic disks, such as floppy disks. Magneto-optical media, and hardware systems specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine code generated by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like. The hardware system described above may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

As described above, the present invention has been described by specific embodiments such as specific components and the like. For those skilled in the art to which the present invention pertains, various modifications and variations are possible.

Therefore, the spirit of the present invention should not be limited to the described embodiments, and all of the equivalents or equivalents of the claims as well as the claims to be described later will belong to the scope of the present invention. .

1 is a block diagram of a search system based on a usage purpose according to an embodiment of the present invention.

2 is a flowchart illustrating a search method based on a use purpose in an embodiment of the present invention.

3 is an example of a process of setting the direction of a keyword according to an embodiment of the present invention.

4 is an example of a process of selecting an indicator for each purpose of use according to an embodiment of the present invention.

5 is an example of a process of evaluating the use of a keyword according to an embodiment of the present invention.

6 is a flowchart illustrating a method of classifying a business type of a keyword to be indexed by the indicator module 101 according to an exemplary embodiment of the present invention.

Claims (25)

An index module for generating a plurality of indices by indexing attributes and associations of keywords; An indicator selection module configured to select at least one of the generated indicators as a weight indicator in correspondence to a purpose for which the keyword is to be used; A weight correction module for changing an index value by applying a weight to the weight indicator; A simulation module for evaluating the keyword based on the generated index including the weighted index in which the index value is changed; And A search module for providing the keyword according to the use of the keyword based on the evaluation of the keyword Search system based on the intended use comprising a. The method of claim 1, The indicator selection module identifies a significant point corresponding to the purpose for which the keyword is to be used, sets the directionality of a condition necessary for the purpose in which the keyword is to be used based on the significant point, and selects the weight indicator based on the directionality. that Retrieval system based on usage, characterized in that. The method of claim 1, The simulation module evaluates the effect of the keyword provided by the search module using a specific indicator. Retrieval system based on usage, characterized in that. The method of claim 1, The simulation module generates a ranking logic evaluation indicator based on the weight indicator and the generated indicator, the indicator value of which is changed, classifies the indicator included in the ranking logic evaluation indicator, and corresponds to the values of the classified indicator. Correcting priorities and proportions Retrieval system based on usage, characterized in that. 5. The method of claim 4, The ranking logic evaluation indicator may include at least one of a competition indicator indicating competition of an advertisement, a service indicator indicating a visit amount of a user, a conversion indicator indicating a click-to-exposure ratio, a conversion indicator indicating an association degree, and an entry indicator indicating a difficulty level of an entry barrier. Containing one Retrieval system based on usage, characterized in that. The method of claim 5, The simulation module corrects the priority to the highest level by judging that the values of the service indicator, the conversion indicator, and the related indicator are high, while the values of the entry indicator and the competition indicator are low, and are necessary keywords to increase the scatter. that Retrieval system based on usage, characterized in that. The method of claim 5, The simulation module, if the values of the entry indicator and the competition indicator are high and the values of the service indicator, the conversion indicator, and the related indicator are low, determine the keywords necessary for promotion and correct the priority to the middle. Retrieval system based on usage, characterized in that. delete The method of claim 1, The keyword is a keyword included in the set of sales top keywords classified business type Retrieval system based on usage, characterized in that. 10. The method of claim 9, The keyword is a keyword included in a keyword pool further including a keyword extracted from another source in the set of the top keywords for sales Retrieval system based on usage, characterized in that. The method of claim 10, The other source may include at least one of a keyword that generates a predetermined number of views by keyword, news, blogs, intellectuals, shopping, site crawling, shopping mall query information, and issue keyword. Retrieval system based on usage, characterized in that. The method of claim 11, The keywords included in the keyword pool are keywords classified according to the keyword industry and the advertiser industry. Retrieval system based on usage, characterized in that. Generating a plurality of indices by indexing attributes and associations of keywords; Selecting at least one of the generated indicators as a weight indicator in correspondence to the use of the keyword; Changing an indicator value by applying a weight to the weight indicator; Evaluating the keyword based on the generated indicator including the weight indicator with the changed indicator value; Providing the keyword according to the purpose for which the keyword is to be used based on the evaluation of the keyword. Search method based on the use, including. The method of claim 13, Generating the indicator, Identifying a significant point corresponding to the purpose for which the keyword is to be used; Setting a direction of a condition necessary for the use of the keyword based on the significant point; And, Selecting the weight indicator based on the directionality Search method based on the use, characterized in that it comprises a. The method of claim 13, Evaluating the effect of the keyword provided in the step of providing the keyword using a specific indicator Search method based on the use, characterized in that it further comprises. The method of claim 13, Evaluating the keyword, Generating a ranking logic evaluation index on the basis of the weighted index with the changed index value and the generated index; Classifying indicators included in the ranking logic evaluation indicators; Correcting the priority and ratio of the keyword in response to the values of the classified indicators. Search method based on the use, characterized in that it comprises a. The method of claim 16, The ranking logic evaluation indicator may include at least one of a competition indicator indicating competition of an advertisement, a service indicator indicating a visit amount of a user, a conversion indicator indicating a click-to-exposure ratio, a conversion indicator indicating an association degree, and an entry indicator indicating a difficulty level of an entry barrier. Containing one A search method based on a use purpose, characterized by the above. The method of claim 17, In the evaluating of the keyword, if the value of the entry indicator and the competition indicator is low and the value of the service indicator, the conversion indicator, and the related indicator is high, the keyword is determined to be a keyword necessary to increase the degree of dispersion. Correcting A search method based on a use purpose, characterized by the above-mentioned. The method of claim 17, In the evaluating of the keyword, if the value of the entry indicator and the competition indicator is high and the value of the service indicator, the conversion indicator, and the related indicator is low, the keyword is determined as a keyword necessary for promotion and the priority is corrected. that A search method based on a use purpose, characterized by the above-mentioned. delete The method of claim 13, The keyword is a keyword included in the set of sales top keywords classified business type A search method based on a use purpose, characterized by the above-mentioned. The method of claim 21, The keyword is a keyword included in a keyword pool further including a keyword extracted from another source in the set of the top keywords for sales A search method based on a use purpose, characterized by the above. The method of claim 22, The other source may include at least one of a keyword that generates a predetermined number of views by keyword, news, blogs, intellectuals, shopping, site crawling, shopping mall query information, and issue keyword. A search method based on a use purpose, characterized by the above-mentioned. 24. The method of claim 23, The keywords included in the keyword pool are keywords classified according to the keyword industry and the advertiser industry. A search method based on a use purpose, characterized by the above-mentioned. A computer-readable recording medium in which a program for executing the method of any one of claims 13 to 19 and 21 to 24 is recorded.

Images